© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 1657
    Prev
    Next
    INDEX
    Explanations

    references to specific Star Wars characters and costumes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    486
    +0.07
    0.2%
    528
    +0.07
    0.2%
    1482
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.07
    0.04
    283
    +0.07
    0.01
    1167
    +0.06
    0.02
    Negative Logits
    diğini
    -0.99
    miyor
    -0.99
    diğ
    -0.94
    diğinde
    -0.94
    miyorum
    -0.92
    diğimiz
    -0.89
    diğim
    -0.86
    mekte
    -0.86
    mişti
    -0.84
    diğiniz
    -0.83
    POSITIVE LOGITS
    me
    2.35
     mef
    1.69
     mme
    1.68
     squa
    1.60
    ME
    1.58
     fta
    1.51
     maneu
    1.44
     huma
    1.41
     lola
    1.41
     ftu
    1.40
    Activations Density 0.217%

    No Known Activations